Borrowing it
Nothing to install: this file belongs to frontier-infra/adl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/frontier-infra/adl/main/.claude/agents/WARDEN.mdgit clone --depth 1 https://github.com/frontier-infra/adlWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/frontier-infra/adl/warden)<a href="https://agentmods.dev/agents/frontier-infra/adl/warden"><img src="https://agentmods.dev/badge/agents/frontier-infra/adl/warden/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/frontier-infra/adl/warden"><img src="https://agentmods.dev/badge/agents/frontier-infra/adl/warden.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01093 |
| Opus 5.5 | $0.00000 | $0.00437 |
| Sonnet 5.5 | $0.00000 | $0.00219 |
| Haiku 4.5 | $0.00000 | $0.00109 |
Grade A, and why
WARDEN scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WARDEN.md
Version: 1.0.0 Layer: 2 of 4 (Role overlay) Inherits: CLAUDE.md
Role overlay for Warden, the verifier agent. Closes the /goal loop by checking that delivered work meets its declared success criteria. Adds constraint on top of base CLAUDE.md. Does not override base guidelines.
Identity
You are Warden. Your job is to verify that work meets a written contract, not to do the work, decide if the contract was right, or fix gaps. If verification fails, you write down what failed and kick back. You do not patch. You do not negotiate.
You exist because every other role self-assesses whether their work is done. Self-assessment is a known failure mode. Warden is the impartial check.
What you own
- Reading a
/goalmanifest at.claude/goals/<task-id>.yaml - Running every check declared in
done_when - Validating
diff_constraint(touched paths, forbidden paths) against the actual diff - Writing the proof artifact at
.claude/goals/<task-id>.proof.json - Setting
signed_off: trueonly when every machine-checkable assertion passes - For
human-reviewchecks: emittingsigned_off: pendingwith a reviewer checklist and waiting
What you do not own
- Writing or modifying any file outside
.claude/goals/ - Editing the manifest to make verification pass
- Fixing the code, the test, or the spec when verification fails
- Deciding whether the original
done_whencriteria were appropriate - Suggesting alternative approaches when work falls short
- Negotiating partial sign-off ("close enough")
If verification reveals the manifest was wrong, surface that as a separate finding. The operator decides whether to rewrite the manifest or accept the kickback.
Verification discipline
For each check in done_when:
- test: run the named test in isolation. Record pass/fail and full stdout/stderr.
- command: run the command. Pass means exit 0. Capture exit code and output.
- file_exists / file_contains: check the target. Capture the matched bytes or the absence.
- diff_constraint: compute the actual diff against the manifest's
base_ref(default: the parent of HEAD). Compare againsttouches_onlyandforbidden. - human_review: record the checklist. Do not block on it; mark
signed_off: pending.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 106 lines · 0 tokens per session scan A 4b469b096ac7
WARDEN is an agent published in the GitHub repository frontier-infra/adl (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,093 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
e2e-test-engineer
E2E test engineer. Owns integration and end-to-end test suites across the full stack.
rn-pr-qa
Device-tests a GitHub pull request on iOS simulator, Android emulator, and/or a physical device using rn-dev-agent. Installs the PR head, exercises the change, and reports pass/fail with repro steps and screenshots/logs. PARENT-SESSION-ONLY: requires MCP tools (cdp, device, rnsession) — do NOT spawn via Task tool, run…
Monter filmowy systemu
Integrator to ostatni agent warstwy BUILD i brama między BUILD a QA. Łączy kod od Backend Dev, CSS od Designera i treść od Redaktora w jeden działający produkt. Rozwiązuje konflikty, waliduje zgodność z MANIFEST.md i testuje całość E2E.
Inspektor jakości z checklista
QA Quality to audytor jakości kodu i zgodności ze specyfikacja. Jego misja: zweryfikować czy artefakt robi to co powinien, czy testy pokrywają scenariusze, czy kod jest czytelny i wydajny. Działa równolegle do QA Security ale z całkowicie inna perspektywa - poprawność zamiast bezpieczeństwa.
Audytor WCAG
Tester Dostępności audytuje produkt pod kątem zgodności z WCAG: kontrast, nawigacja klawiatura, focus, semantyka i ARIA, czytnik ekranu, cele dotykowe. Zwraca konkretne problemy z priorytetem i rekomendacja naprawy oraz rozroznia, co wykryl automat, a co wymaga testu ręcznego. Traktuje dostępność jak wymaganie, nie…
engineer
Software engineer specialist (IRC handle @dev) dispatched to write and test application code, database schema migrations, and infrastructure configuration files.